Applying artificial neural networks to modeling the middle atmosphere
Tóm tắt
An artificial neural network (ANN) is used to model the middle atmosphere using a large number of TIMED/SABER limb sounding temperature profiles. A three-layer feed-forward network is chosen based on the back-propagation (BP) algorithm. Latitude, longitude, and height are chosen as the input vectors of the network while temperature is the output vector. The temperature observations during the period from 13 January through 16 March 2007, which are in the same satellite yaw, are taken as samples to train an ANN. Results suggest that the network has high quality for modeling spatial variations of temperature. Quantitative comparisons between the ANN outputs and those from the popular empirical NRLMSISE-00 model illustrate their generally consistent features and some specific differences. The NRLMSISE-00 model’s zonal mean temperatures are too high by ∼6 K-10 K near the stratopause, and the amplitude and phase of the planetary wave number 1 activity are different in some respects from the ANN simulations above 45–50 km, suggesting improvement is needed in the NRLMSISE-00 model for more accurate simulation near and above the stratopause.
Tài liệu tham khảo
Evensen, G., 1992: Using the extended Kalman filter with a multilayer quasi-geostrophic ocean model. J. Geophys. Res., 97, 17904–17905.
Hedin, A. E., 1987: MSIS-86 thermospheric model. J. Geophys. Res., 92(A5), 4649–4662.
Hu, X., Z. R. Huang, X. X. Zhang, J. C. Gong, B. S. Xue, and Z. H. Ye, 1998: Warming of solar proton events. Chinese Journal of Space Science, 18(4), 323–328. (in Chinese)
Jarvinen, H., N. T. Jean, and C. Phillippe, 1995: Quasi-continuous variational data assimilation. ECMWF Research Dept. Tech. Memo., 210pp.
Labitzke, K., J. J. Barnett, and B. Edwards, 1985: Handbook MAP 16. SCOSTEP, University of Illinois, Urbana, 318pp.
Mertens, C. J., M. G. Mlynczak, M. Lopez-Puertas, P. P. Wintersteiner, R. H. Picard, J. R. Winick, L. L. Gordley, and J. M. Russell III, 2001: Retrieval of mesospheric and lower thermospheric kinetic temperature from measurements of CO2 15-µm Earth limb emission under non-LTE conditions. Geophys. Res. Lett., 28, 1391–1394.
Mertens, C. J., and Coauthors, 2004: SABER observations of mesospheric temperature and comparisons with falling sphere measurements taken during the 2002 summer MaCWAVE campaign. Geophys. Res. Lett., 31, L03105, doi: 10.1029/2003GL018605.
Moller, M. F., 1993: A scaled conjugate gradient algorithm for fast supervised learning. Neural Networks, 6, 525–533.
Picone, J. M., A. E. Hedin, D. P. Drob, and A. C. Aikin, 2002: NRLMSISE-00 empirical model of the atmosphere: Statistical comparisons and scientific issues. J. Geophys. Res., 107(A12), 1468, doi: 10.1029/2002JA009430.
Remsberg, E., G. Lingenfelser, V. L. Harvey, W. Grose, J. Russell III, M. Mlynczak, L. Gordley, and B. T. Marshall, 2003: On the verification of the quality of SABER temperature, geopotential height, and wind fields by comparison with Met Office assimilated analyses. J. Geophys. Res., 108(D20), 4628, doi: 10.1029/2003JD003720.
Remsberg, E. E., and Coauthors, 2008: Assessment of the quality of the Version 1.07 temperature-versus-pressure profiles of the middle atmosphere from TIMED/SABER. J. Geophys. Res., 113, D17101, doi: 10.1029/2008JD010013.
Wang, X., and D. R. Lü, 2005: Retrieval of water vapor profiles with radio occultation measurements using an artificial neural network. Adv. Atmos. Sci., 22(5), 759–764.
Wu, X. D., H. X. Cao, F. Andrew, F. Y. Wei, and G. L. Feng, 2001: Forecasting monsoon precipitation using artificial neural networks. Adv. Atmos. Sci., 18(5), 950–958.
Xiao, C. Y., X. Hu, X. X. Zhang, D. Y. Zhang, X. C. Wu, X. Y. Gong, and K. Igarashi, 2007: Interpretation of the mesospheric and lower thermospheric mean winds observed by MF radar at about 30°N with the 2D-SOCRATES model. Advances in Space Research, 39(8), 1267–1277.
Xiao, C., X. Hu, and J. Tian, 2009: Global temperature stationary planetary waves extending from 20 to 120 km observed by TIMED/SABER. J. Geophys. Res., 114, D17101, doi: 10.1029/2008JD011349.
Zeng, Z., X. Hu, and X. Zhang, 2002: Applying artificial neural network to the short-term prediction of electron density structure using GPS occultation data. Geophys. Res. Lett., 29(9), 1321, doi: 10.1029/2001GL013656.
Zhang, X. J., W. Zeng, and X. Hu, 1996: A study of ionospheric parameters using the artificial neural net. Chinese Journal of Radio Science, 11(3), 14–21. (in Chinese)
Zhang, X., J. M. Forbes, M. E. Hagan, J. M. Russell III, S. E. Palo, C. J. Mertens, and M. G. Mlynczakm, 2006: Monthly tidal temperatures 20–120 km from TIMED/SABER. J. Geophys. Res., 111, A10S08, doi: 10.1029/2005JA011504.